Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 433 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7223. Min Range: -6.7223
Max Act: 6.7223. Min Act: -0.1700
Data Index: 498618 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7223. Min Range: -6.7223
Max Act: 6.5973. Min Act: -0.1700
Data Index: 4093626 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7223. Min Range: -6.7223
Max Act: 6.5348. Min Act: -0.1700
Data Index: 5536051 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7223. Min Range: -6.7223
Max Act: 6.5035. Min Act: -0.1700
Data Index: 134223 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7223. Min Range: -6.7223
Max Act: 6.5035. Min Act: -0.1700
Data Index: 8068776 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7223. Min Range: -6.7223
Max Act: 6.4410. Min Act: -0.1700
Data Index: 6867253 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7223. Min Range: -6.7223
Max Act: 6.3785. Min Act: -0.1700
Data Index: 1960704 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7223. Min Range: -6.7223
Max Act: 6.3473. Min Act: -0.1700
Data Index: 8508190 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7223. Min Range: -6.7223
Max Act: 6.3473. Min Act: -0.1700
Data Index: 564932 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7223. Min Range: -6.7223
Max Act: 6.3160. Min Act: -0.1700
Data Index: 5094412 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7223. Min Range: -6.7223
Max Act: 6.3473. Min Act: -0.1700
Data Index: 6044164 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7223. Min Range: -6.7223
Max Act: 6.3160. Min Act: -0.1700
Data Index: 3025498 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7223. Min Range: -6.7223
Max Act: 6.3160. Min Act: -0.1700
Data Index: 7138240 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7223. Min Range: -6.7223
Max Act: 6.2848. Min Act: -0.1700
Data Index: 4554760 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7223. Min Range: -6.7223
Max Act: 6.2848. Min Act: -0.1700
Data Index: 5710233 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7223. Min Range: -6.7223
Max Act: 6.2535. Min Act: -0.1700
Data Index: 5817937 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7223. Min Range: -6.7223
Max Act: 6.2223. Min Act: -0.1700
Data Index: 3262259 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7223. Min Range: -6.7223
Max Act: 6.2535. Min Act: -0.1700
Data Index: 4240528 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7223. Min Range: -6.7223
Max Act: 6.2223. Min Act: -0.1700
Data Index: 1462664 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7223. Min Range: -6.7223
Max Act: 6.2535. Min Act: -0.1700
Data Index: 944833 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19